How to create your own Chibi-style 3D selfie diorama in minutes. Here’s the prompt for Nano Banana Pro

A viral artificial intelligence trend is gaining momentum in the tech and creator communities, as social media users generate isometric 3D cube scenes showing miniature versions of themselves inside cosy, carefully designed rooms, using the Nano Banana Pro.

The images resemble collectible display pieces or small diorama lamps, often featuring warm internal lighting, realistic textures and chibi-style figurines. Shared widely on X and other platforms, the visuals have drawn attention for their blend of realism, cuteness and personalisation.

Nano Banana Pro spotlights the trend

The trend received a major boost after AI creator Nano Banana Pro shared a ready-to-use prompt on Friday, encouraging users to experiment with the style. The post explained how a simple description of a person, an activity and a setting could be transformed into a polished 3D cube scene using generative AI tools.

Nano Banana Pro wrote that the goal was to create “cute little diorama lamps”, focusing on enclosed cube compositions, soft lighting and small imperfections that make the scene feel tangible rather than purely digital.

Prompt shared by Nano Banana Pro

Prompt:
A [subject] is [doing something] in a [place]. Isometric 3D cube diorama with internal lighting, cute chibi figurine style, matte PVC material, big head/small body. Neutral background on a table in a dark room. Enclosed in a cube. Fill the diorama with many cute little details. Add delicate imperfections like dust, scratches and textures to make it real.

Credit given to community inspiration

In a follow-up post shared yesterday, Nano Banana Pro thanked X user @Arminn_Ai for inspiring the prompt structure and reshared their earlier tweet. @Arminn_Ai had posted on 8 December, showcasing examples of 3D miniature isometric rooms and inviting users to generate personalised versions by uploading their own photos.

The post offered to share full prompts with interested users, helping others replicate and build on the visual style.

@Arminn_Ai’s version of the prompt goes deeper into scene-building, asking users to define the room layout, décor and clutter in detail, while also translating their real-life appearance into a figurine-like character. The emphasis is on keeping everything strictly inside the cube and maintaining a clean, isometric viewpoint.

Prompt shared by X user @Arminn_Ai

Prompt:
An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is [ROOM DESCRIPTION: Describe the theme, furniture, specific clutter, wall decorations, and key items in detail].

Character: a chibi/figurine-style — [INSERT DESCRIPTION OF THE PERSON FROM YOUR UPLOADED PHOTO HERE]. The character is [ACTION: e.g., sitting on a chair typing, standing and cooking, playing guitar], with a [EXPRESSION: e.g., focused, happy, smiling] expression. Figure material looks like matte PVC, with big head / small body proportions.

Lighting: [ATMOSPHERE NAME]: [LIGHT SOURCES: e.g., neon blue glow, warm sunlight, golden lamp light]; realistic reflections and coloured shadows.

Camera: slightly elevated isometric three-quarter view, front cube edge centred; no elements protruding outside the cube.

Photoreal materials with fine detail; neutral backdrop. Ultra-detailed, clean composition; no watermark.

Why the trend is resonating

The appeal of the cube dioramas lies in their mix of nostalgia, creativity and self-expression, just like the Chibi and Ghibli trend. Moreover, the scenes resemble dollhouses, desk toys or decorative lamps, while also demonstrating how far text-to-image AI tools have evolved.

By combining personal photos with detailed prompts, users can now produce images that look like professionally designed 3D models, without needing specialist software or technical skills.